Nuo Chen

works on

benchmark 1 computer-use agents 1 cross-platform evaluation 1 document organization 1 language model pretraining 1 mid-training 1 reward modeling 1 synthetic data generation 1 textbook synthesis 1 vision-language models 1

From the 2 of 29 linked papers with an AI index.

activity

20242026

collaborators

Showing cs.CYShow all

1 paper · 1 filter

cs.CY2026

Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning

Qian Wang, Xuandong Zhao, Zirui Zhang +4

Large language models (LLMs) increasingly serve as reasoners and automated evaluators, yet they remain susceptible to cognitive biases -- often altering their reasoning when faced…